303 citations
- Politecnico di TorinoIT17 papers
- Sapienza University of RomeIT12 papers
- University of TurinIT10 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Collegio Carlo AlbertoIT9 papers
- Decision Sciences (United States)US7 papers
- École Polytechnique Fédérale de LausanneCH7 papers
- The Abdus Salam International Centre for Theoretical Physics (ICTP)IT7 papers
- The University of Texas at AustinUS7 papers
- University of MilanIT7 papers
- Institute for Complex SystemsIT6 papers
- Istituto Nazionale di Fisica NucleareIT6 papers
17 papers · 1 filter
Neural Diffusion Processes for Physically Interpretable Survival Prediction
Alessio Cristofoletto, Cesare Rollo, Giovanni Birolo +1
We introduce DeepFHT, a survival-analysis framework that couples deep neural networks with first hitting time (FHT) distributions from stochastic process theory. Time to event is r…
GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia
Carlo Lucibello, Aurora Rossi
GraphNeuralNetworks.jl is an open-source framework for deep learning on graphs, written in the Julia programming language. It supports multiple GPU backends, generic sparse or dens…
How transformers learn structured data: insights from hierarchical filtering
Jerome Garnier-Brun, Marc Mézard, Emanuele Moscato +1
Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introdu…
A novel approach to graph distinction through GENEOs and permutants
Giovanni Bocchi, Massimo Ferri, Patrizio Frosini
The theory of Group Equivariant Non-Expansive Operators (GENEOs) was initially developed in Topological Data Analysis for the geometric approximation of data observers, including t…
Dynamical Regimes of Diffusion Models
Giulio Biroli, Tony Bonnaire, Valentin de Bortoli +1
Using statistical physics methods, we study generative diffusion models in the regime where the dimension of space and the number of data are large, and the score function has been…
Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
Arthur da Cunha, Francesco d'Amore, Emanuele Natale
The Strong Lottery Ticket Hypothesis (SLTH) states that randomly-initialised neural networks likely contain subnetworks that perform well without any training. Although unstructure…